A Graph Neural Network Approach to Molecule Carcinogenicity Prediction

Abstract

Molecular carcinogenicity is a preventable cause of cancer, however, most experimental testing of molecular compounds is an expensive and time consuming process, making high throughput experimental approaches infeasible. In recent years, there has been substantial progress in machine learning techniques for molecular property prediction. In this work, we propose a model for carcinogenicity prediction, CONCERTO, which uses a graph transformer in conjunction with a molecular fingerprint representation, trained on multi-round muta-genicity and carcinogenicity objectives. To train and validate CONCERTO, we augment the training dataset with more informative labels and utilize a larger external validation dataset. Extensive experiments demonstrate that our model yields results superior to alternate approaches for molecular carcinogenicity prediction.

Deep active learning with high structural discriminability for molecular mutagenicity prediction

“…Researchers have proposed some deep learning methods aimed at accurately predicting molecular mutagenicity [13][14][15][16][17] . However, the scarcity of labeled data limits the performance of in silico methods in prediction tasks 18,19 .…”